TmpModel / saves /chess /no_explain /trainer_log.jsonl
reasonwang's picture
Upload folder using huggingface_hub
a1506a1 verified
{"current_steps": 100, "total_steps": 12480, "loss": 1.3897, "lr": 4.006410256410257e-07, "epoch": 0.08009611533840609, "percentage": 0.8, "elapsed_time": "0:04:40", "remaining_time": "9:38:28"}
{"current_steps": 200, "total_steps": 12480, "loss": 0.0598, "lr": 8.012820512820515e-07, "epoch": 0.16019223067681218, "percentage": 1.6, "elapsed_time": "0:09:11", "remaining_time": "9:24:06"}
{"current_steps": 300, "total_steps": 12480, "loss": 0.0551, "lr": 1.201923076923077e-06, "epoch": 0.24028834601521826, "percentage": 2.4, "elapsed_time": "0:13:43", "remaining_time": "9:16:55"}
{"current_steps": 400, "total_steps": 12480, "loss": 0.0516, "lr": 1.602564102564103e-06, "epoch": 0.32038446135362436, "percentage": 3.21, "elapsed_time": "0:18:48", "remaining_time": "9:27:55"}
{"current_steps": 500, "total_steps": 12480, "loss": 0.0501, "lr": 2.0032051282051286e-06, "epoch": 0.4004805766920304, "percentage": 4.01, "elapsed_time": "0:23:18", "remaining_time": "9:18:38"}
{"current_steps": 600, "total_steps": 12480, "loss": 0.0486, "lr": 2.403846153846154e-06, "epoch": 0.4805766920304365, "percentage": 4.81, "elapsed_time": "0:27:49", "remaining_time": "9:10:52"}
{"current_steps": 700, "total_steps": 12480, "loss": 0.0463, "lr": 2.8044871794871797e-06, "epoch": 0.5606728073688426, "percentage": 5.61, "elapsed_time": "0:32:36", "remaining_time": "9:08:45"}
{"current_steps": 800, "total_steps": 12480, "loss": 0.0447, "lr": 3.205128205128206e-06, "epoch": 0.6407689227072487, "percentage": 6.41, "elapsed_time": "0:38:34", "remaining_time": "9:23:16"}
{"current_steps": 900, "total_steps": 12480, "loss": 0.0441, "lr": 3.605769230769231e-06, "epoch": 0.7208650380456548, "percentage": 7.21, "elapsed_time": "0:43:53", "remaining_time": "9:24:43"}
{"current_steps": 1000, "total_steps": 12480, "loss": 0.0429, "lr": 4.006410256410257e-06, "epoch": 0.8009611533840608, "percentage": 8.01, "elapsed_time": "0:48:23", "remaining_time": "9:15:32"}
{"current_steps": 1000, "total_steps": 12480, "eval_loss": 0.042210426181554794, "epoch": 0.8009611533840608, "percentage": 8.01, "elapsed_time": "0:50:00", "remaining_time": "9:34:08"}
{"current_steps": 1100, "total_steps": 12480, "loss": 0.0414, "lr": 4.4070512820512826e-06, "epoch": 0.8810572687224669, "percentage": 8.81, "elapsed_time": "0:55:40", "remaining_time": "9:35:57"}
{"current_steps": 1200, "total_steps": 12480, "loss": 0.0402, "lr": 4.807692307692308e-06, "epoch": 0.961153384060873, "percentage": 9.62, "elapsed_time": "1:00:10", "remaining_time": "9:25:41"}
{"current_steps": 1300, "total_steps": 12480, "loss": 0.0386, "lr": 4.999735579817769e-06, "epoch": 1.0408490188225872, "percentage": 10.42, "elapsed_time": "1:04:57", "remaining_time": "9:18:40"}
{"current_steps": 1400, "total_steps": 12480, "loss": 0.0373, "lr": 4.997740994288484e-06, "epoch": 1.1209451341609933, "percentage": 11.22, "elapsed_time": "1:09:28", "remaining_time": "9:09:46"}
{"current_steps": 1500, "total_steps": 12480, "loss": 0.0366, "lr": 4.993792498360407e-06, "epoch": 1.2010412494993994, "percentage": 12.02, "elapsed_time": "1:13:57", "remaining_time": "9:01:25"}
{"current_steps": 1600, "total_steps": 12480, "loss": 0.0357, "lr": 4.9878931808274796e-06, "epoch": 1.2811373648378055, "percentage": 12.82, "elapsed_time": "1:18:28", "remaining_time": "8:53:34"}
{"current_steps": 1700, "total_steps": 12480, "loss": 0.0352, "lr": 4.980047656554856e-06, "epoch": 1.3612334801762114, "percentage": 13.62, "elapsed_time": "1:23:22", "remaining_time": "8:48:39"}
{"current_steps": 1800, "total_steps": 12480, "loss": 0.0346, "lr": 4.970262062868821e-06, "epoch": 1.4413295955146175, "percentage": 14.42, "elapsed_time": "1:28:25", "remaining_time": "8:44:41"}
{"current_steps": 1900, "total_steps": 12480, "loss": 0.0336, "lr": 4.958544054755741e-06, "epoch": 1.5214257108530236, "percentage": 15.22, "elapsed_time": "1:33:34", "remaining_time": "8:41:03"}
{"current_steps": 2000, "total_steps": 12480, "loss": 0.0329, "lr": 4.944902798873794e-06, "epoch": 1.6015218261914297, "percentage": 16.03, "elapsed_time": "1:38:03", "remaining_time": "8:33:50"}
{"current_steps": 2000, "total_steps": 12480, "eval_loss": 0.03361953794956207, "epoch": 1.6015218261914297, "percentage": 16.03, "elapsed_time": "1:39:40", "remaining_time": "8:42:20"}
{"current_steps": 2100, "total_steps": 12480, "loss": 0.0328, "lr": 4.92934896638215e-06, "epoch": 1.6816179415298358, "percentage": 16.83, "elapsed_time": "1:45:26", "remaining_time": "8:41:13"}
{"current_steps": 2200, "total_steps": 12480, "loss": 0.0316, "lr": 4.91189472459324e-06, "epoch": 1.761714056868242, "percentage": 17.63, "elapsed_time": "1:49:57", "remaining_time": "8:33:46"}
{"current_steps": 2300, "total_steps": 12480, "loss": 0.0317, "lr": 4.892553727454616e-06, "epoch": 1.841810172206648, "percentage": 18.43, "elapsed_time": "1:54:27", "remaining_time": "8:26:34"}
{"current_steps": 2400, "total_steps": 12480, "loss": 0.0309, "lr": 4.8713411048678635e-06, "epoch": 1.921906287545054, "percentage": 19.23, "elapsed_time": "1:58:56", "remaining_time": "8:19:34"}
{"current_steps": 2500, "total_steps": 12480, "loss": 0.0305, "lr": 4.848273450852921e-06, "epoch": 2.0016019223067683, "percentage": 20.03, "elapsed_time": "2:03:25", "remaining_time": "8:12:41"}
{"current_steps": 2600, "total_steps": 12480, "loss": 0.0268, "lr": 4.823368810567056e-06, "epoch": 2.0816980376451744, "percentage": 20.83, "elapsed_time": "2:07:54", "remaining_time": "8:06:04"}
{"current_steps": 2700, "total_steps": 12480, "loss": 0.0268, "lr": 4.796646666188663e-06, "epoch": 2.1617941529835805, "percentage": 21.63, "elapsed_time": "2:12:24", "remaining_time": "7:59:38"}
{"current_steps": 2800, "total_steps": 12480, "loss": 0.0272, "lr": 4.768127921676916e-06, "epoch": 2.2418902683219866, "percentage": 22.44, "elapsed_time": "2:17:52", "remaining_time": "7:56:40"}
{"current_steps": 2900, "total_steps": 12480, "loss": 0.0297, "lr": 4.737834886419217e-06, "epoch": 2.3219863836603922, "percentage": 23.24, "elapsed_time": "2:22:28", "remaining_time": "7:50:40"}
{"current_steps": 3000, "total_steps": 12480, "loss": 0.0275, "lr": 4.705791257779196e-06, "epoch": 2.4020824989987988, "percentage": 24.04, "elapsed_time": "2:26:58", "remaining_time": "7:44:26"}
{"current_steps": 3000, "total_steps": 12480, "eval_loss": 0.029653793200850487, "epoch": 2.4020824989987988, "percentage": 24.04, "elapsed_time": "2:28:35", "remaining_time": "7:49:33"}
{"current_steps": 3100, "total_steps": 12480, "loss": 0.0269, "lr": 4.672022102558958e-06, "epoch": 2.4821786143372044, "percentage": 24.84, "elapsed_time": "2:34:19", "remaining_time": "7:46:57"}
{"current_steps": 3200, "total_steps": 12480, "loss": 0.0269, "lr": 4.636553837390051e-06, "epoch": 2.562274729675611, "percentage": 25.64, "elapsed_time": "2:38:50", "remaining_time": "7:40:37"}
{"current_steps": 3300, "total_steps": 12480, "loss": 0.026, "lr": 4.5994142080684956e-06, "epoch": 2.6423708450140166, "percentage": 26.44, "elapsed_time": "2:43:20", "remaining_time": "7:34:23"}
{"current_steps": 3400, "total_steps": 12480, "loss": 0.026, "lr": 4.560632267850054e-06, "epoch": 2.7224669603524227, "percentage": 27.24, "elapsed_time": "2:47:51", "remaining_time": "7:28:16"}
{"current_steps": 3500, "total_steps": 12480, "loss": 0.0257, "lr": 4.5202383547227134e-06, "epoch": 2.802563075690829, "percentage": 28.04, "elapsed_time": "2:52:21", "remaining_time": "7:22:13"}
{"current_steps": 3600, "total_steps": 12480, "loss": 0.0256, "lr": 4.478264067674155e-06, "epoch": 2.882659191029235, "percentage": 28.85, "elapsed_time": "2:56:52", "remaining_time": "7:16:16"}
{"current_steps": 3700, "total_steps": 12480, "loss": 0.0255, "lr": 4.43474224197278e-06, "epoch": 2.962755306367641, "percentage": 29.65, "elapsed_time": "3:01:22", "remaining_time": "7:10:24"}
{"current_steps": 3800, "total_steps": 12480, "loss": 0.0224, "lr": 4.389706923481633e-06, "epoch": 3.0424509411293554, "percentage": 30.45, "elapsed_time": "3:05:51", "remaining_time": "7:04:33"}
{"current_steps": 3900, "total_steps": 12480, "loss": 0.0198, "lr": 4.34319334202531e-06, "epoch": 3.122547056467761, "percentage": 31.25, "elapsed_time": "3:10:21", "remaining_time": "6:58:46"}
{"current_steps": 4000, "total_steps": 12480, "loss": 0.0202, "lr": 4.2952378838306855e-06, "epoch": 3.202643171806167, "percentage": 32.05, "elapsed_time": "3:14:50", "remaining_time": "6:53:03"}
{"current_steps": 4000, "total_steps": 12480, "eval_loss": 0.029243575409054756, "epoch": 3.202643171806167, "percentage": 32.05, "elapsed_time": "3:16:28", "remaining_time": "6:56:30"}
{"current_steps": 4100, "total_steps": 12480, "loss": 0.0205, "lr": 4.245878063063022e-06, "epoch": 3.2827392871445733, "percentage": 32.85, "elapsed_time": "3:23:36", "remaining_time": "6:56:10"}
{"current_steps": 4200, "total_steps": 12480, "loss": 0.0205, "lr": 4.195152492479727e-06, "epoch": 3.3628354024829794, "percentage": 33.65, "elapsed_time": "3:28:05", "remaining_time": "6:50:13"}
{"current_steps": 4300, "total_steps": 12480, "loss": 0.0204, "lr": 4.143100853224714e-06, "epoch": 3.4429315178213855, "percentage": 34.46, "elapsed_time": "3:32:34", "remaining_time": "6:44:22"}
{"current_steps": 4400, "total_steps": 12480, "loss": 0.0204, "lr": 4.089763863786988e-06, "epoch": 3.5230276331597916, "percentage": 35.26, "elapsed_time": "3:37:04", "remaining_time": "6:38:36"}
{"current_steps": 4500, "total_steps": 12480, "loss": 0.0201, "lr": 4.035183248147752e-06, "epoch": 3.6031237484981977, "percentage": 36.06, "elapsed_time": "3:41:34", "remaining_time": "6:32:55"}
{"current_steps": 4600, "total_steps": 12480, "loss": 0.02, "lr": 3.979401703140955e-06, "epoch": 3.683219863836604, "percentage": 36.86, "elapsed_time": "3:46:04", "remaining_time": "6:27:16"}
{"current_steps": 4700, "total_steps": 12480, "loss": 0.0206, "lr": 3.922462865052782e-06, "epoch": 3.76331597917501, "percentage": 37.66, "elapsed_time": "3:50:35", "remaining_time": "6:21:41"}
{"current_steps": 4800, "total_steps": 12480, "loss": 0.0199, "lr": 3.8644112754862614e-06, "epoch": 3.843412094513416, "percentage": 38.46, "elapsed_time": "3:55:04", "remaining_time": "6:16:07"}
{"current_steps": 4900, "total_steps": 12480, "loss": 0.0199, "lr": 3.805292346517659e-06, "epoch": 3.923508209851822, "percentage": 39.26, "elapsed_time": "3:59:34", "remaining_time": "6:10:36"}
{"current_steps": 5000, "total_steps": 12480, "loss": 0.0194, "lr": 3.745152325171921e-06, "epoch": 4.0032038446135365, "percentage": 40.06, "elapsed_time": "4:04:02", "remaining_time": "6:05:05"}
{"current_steps": 5000, "total_steps": 12480, "eval_loss": 0.02939535118639469, "epoch": 4.0032038446135365, "percentage": 40.06, "elapsed_time": "4:05:40", "remaining_time": "6:07:31"}
{"current_steps": 5100, "total_steps": 12480, "loss": 0.0109, "lr": 3.6840382572449733e-06, "epoch": 4.083299959951942, "percentage": 40.87, "elapsed_time": "4:11:38", "remaining_time": "6:04:09"}
{"current_steps": 5200, "total_steps": 12480, "loss": 0.0116, "lr": 3.621997950501156e-06, "epoch": 4.163396075290349, "percentage": 41.67, "elapsed_time": "4:16:54", "remaining_time": "5:59:40"}
{"current_steps": 5300, "total_steps": 12480, "loss": 0.0119, "lr": 3.5590799372745915e-06, "epoch": 4.243492190628754, "percentage": 42.47, "elapsed_time": "4:21:24", "remaining_time": "5:54:07"}
{"current_steps": 5400, "total_steps": 12480, "loss": 0.0125, "lr": 3.495333436503753e-06, "epoch": 4.323588305967161, "percentage": 43.27, "elapsed_time": "4:25:54", "remaining_time": "5:48:37"}
{"current_steps": 5500, "total_steps": 12480, "loss": 0.0122, "lr": 3.4308083152289073e-06, "epoch": 4.403684421305567, "percentage": 44.07, "elapsed_time": "4:30:25", "remaining_time": "5:43:11"}
{"current_steps": 5600, "total_steps": 12480, "loss": 0.0121, "lr": 3.3655550495825824e-06, "epoch": 4.483780536643973, "percentage": 44.87, "elapsed_time": "4:34:54", "remaining_time": "5:37:45"}
{"current_steps": 5700, "total_steps": 12480, "loss": 0.0123, "lr": 3.2996246853035417e-06, "epoch": 4.563876651982379, "percentage": 45.67, "elapsed_time": "4:39:24", "remaining_time": "5:32:20"}
{"current_steps": 5800, "total_steps": 12480, "loss": 0.0121, "lr": 3.233068797805194e-06, "epoch": 4.6439727673207845, "percentage": 46.47, "elapsed_time": "4:43:54", "remaining_time": "5:26:59"}
{"current_steps": 5900, "total_steps": 12480, "loss": 0.0121, "lr": 3.1659394518296303e-06, "epoch": 4.724068882659191, "percentage": 47.28, "elapsed_time": "4:48:26", "remaining_time": "5:21:41"}
{"current_steps": 6000, "total_steps": 12480, "loss": 0.0119, "lr": 3.0982891607188948e-06, "epoch": 4.8041649979975976, "percentage": 48.08, "elapsed_time": "4:53:09", "remaining_time": "5:16:36"}
{"current_steps": 6000, "total_steps": 12480, "eval_loss": 0.031129568815231323, "epoch": 4.8041649979975976, "percentage": 48.08, "elapsed_time": "4:54:46", "remaining_time": "5:18:21"}
{"current_steps": 6100, "total_steps": 12480, "loss": 0.0121, "lr": 3.0301708453353118e-06, "epoch": 4.884261113336003, "percentage": 48.88, "elapsed_time": "5:00:29", "remaining_time": "5:14:17"}
{"current_steps": 6200, "total_steps": 12480, "loss": 0.0114, "lr": 2.961637792663032e-06, "epoch": 4.964357228674409, "percentage": 49.68, "elapsed_time": "5:05:00", "remaining_time": "5:08:56"}
{"current_steps": 6300, "total_steps": 12480, "loss": 0.0075, "lr": 2.8927436141231695e-06, "epoch": 5.044052863436123, "percentage": 50.48, "elapsed_time": "5:09:29", "remaining_time": "5:03:35"}
{"current_steps": 6400, "total_steps": 12480, "loss": 0.0044, "lr": 2.8235422036351384e-06, "epoch": 5.12414897877453, "percentage": 51.28, "elapsed_time": "5:13:58", "remaining_time": "4:58:16"}
{"current_steps": 6500, "total_steps": 12480, "loss": 0.0043, "lr": 2.754087695457005e-06, "epoch": 5.2042450941129355, "percentage": 52.08, "elapsed_time": "5:18:27", "remaining_time": "4:52:58"}
{"current_steps": 6600, "total_steps": 12480, "loss": 0.0045, "lr": 2.684434421837821e-06, "epoch": 5.284341209451342, "percentage": 52.88, "elapsed_time": "5:24:17", "remaining_time": "4:48:55"}
{"current_steps": 6700, "total_steps": 12480, "loss": 0.0048, "lr": 2.6146368705150854e-06, "epoch": 5.364437324789748, "percentage": 53.69, "elapsed_time": "5:29:17", "remaining_time": "4:44:04"}
{"current_steps": 6800, "total_steps": 12480, "loss": 0.0045, "lr": 2.5447496420905608e-06, "epoch": 5.444533440128154, "percentage": 54.49, "elapsed_time": "5:33:46", "remaining_time": "4:38:48"}
{"current_steps": 6900, "total_steps": 12480, "loss": 0.0045, "lr": 2.4748274073178114e-06, "epoch": 5.52462955546656, "percentage": 55.29, "elapsed_time": "5:38:17", "remaining_time": "4:33:34"}
{"current_steps": 7000, "total_steps": 12480, "loss": 0.0048, "lr": 2.4049248643348512e-06, "epoch": 5.6047256708049655, "percentage": 56.09, "elapsed_time": "5:42:47", "remaining_time": "4:28:21"}
{"current_steps": 7000, "total_steps": 12480, "eval_loss": 0.04388193413615227, "epoch": 5.6047256708049655, "percentage": 56.09, "elapsed_time": "5:44:24", "remaining_time": "4:29:37"}
{"current_steps": 7100, "total_steps": 12480, "loss": 0.0043, "lr": 2.3350966958753766e-06, "epoch": 5.684821786143372, "percentage": 56.89, "elapsed_time": "5:50:02", "remaining_time": "4:25:14"}
{"current_steps": 7200, "total_steps": 12480, "loss": 0.0043, "lr": 2.265397526492052e-06, "epoch": 5.764917901481779, "percentage": 57.69, "elapsed_time": "5:54:32", "remaining_time": "4:19:59"}
{"current_steps": 7300, "total_steps": 12480, "loss": 0.0043, "lr": 2.195881879825301e-06, "epoch": 5.845014016820184, "percentage": 58.49, "elapsed_time": "5:59:01", "remaining_time": "4:14:45"}
{"current_steps": 7400, "total_steps": 12480, "loss": 0.0043, "lr": 2.1266041359510456e-06, "epoch": 5.92511013215859, "percentage": 59.29, "elapsed_time": "6:03:31", "remaining_time": "4:09:33"}
{"current_steps": 7500, "total_steps": 12480, "loss": 0.004, "lr": 2.057618488840745e-06, "epoch": 6.004805766920304, "percentage": 60.1, "elapsed_time": "6:07:59", "remaining_time": "4:04:20"}
{"current_steps": 7600, "total_steps": 12480, "loss": 0.0014, "lr": 1.9889789039670276e-06, "epoch": 6.084901882258711, "percentage": 60.9, "elapsed_time": "6:12:29", "remaining_time": "3:59:10"}
{"current_steps": 7700, "total_steps": 12480, "loss": 0.0014, "lr": 1.9207390760880605e-06, "epoch": 6.1649979975971165, "percentage": 61.7, "elapsed_time": "6:16:59", "remaining_time": "3:54:02"}
{"current_steps": 7800, "total_steps": 12480, "loss": 0.0013, "lr": 1.852952387243698e-06, "epoch": 6.245094112935522, "percentage": 62.5, "elapsed_time": "6:21:30", "remaining_time": "3:48:54"}
{"current_steps": 7900, "total_steps": 12480, "loss": 0.0013, "lr": 1.7856718649962606e-06, "epoch": 6.325190228273929, "percentage": 63.3, "elapsed_time": "6:26:00", "remaining_time": "3:43:47"}
{"current_steps": 8000, "total_steps": 12480, "loss": 0.0013, "lr": 1.7189501409486061e-06, "epoch": 6.405286343612334, "percentage": 64.1, "elapsed_time": "6:31:09", "remaining_time": "3:39:02"}
{"current_steps": 8000, "total_steps": 12480, "eval_loss": 0.053785648196935654, "epoch": 6.405286343612334, "percentage": 64.1, "elapsed_time": "6:32:46", "remaining_time": "3:39:57"}
{"current_steps": 8100, "total_steps": 12480, "loss": 0.0013, "lr": 1.6528394095719558e-06, "epoch": 6.485382458950741, "percentage": 64.9, "elapsed_time": "6:38:28", "remaining_time": "3:35:28"}
{"current_steps": 8200, "total_steps": 12480, "loss": 0.0014, "lr": 1.587391387375669e-06, "epoch": 6.565478574289147, "percentage": 65.71, "elapsed_time": "6:42:59", "remaining_time": "3:30:20"}
{"current_steps": 8300, "total_steps": 12480, "loss": 0.0013, "lr": 1.522657272450917e-06, "epoch": 6.645574689627553, "percentage": 66.51, "elapsed_time": "6:47:29", "remaining_time": "3:25:12"}
{"current_steps": 8400, "total_steps": 12480, "loss": 0.0014, "lr": 1.4586877044199015e-06, "epoch": 6.725670804965959, "percentage": 67.31, "elapsed_time": "6:51:59", "remaining_time": "3:20:06"}
{"current_steps": 8500, "total_steps": 12480, "loss": 0.0014, "lr": 1.3955327248219438e-06, "epoch": 6.805766920304365, "percentage": 68.11, "elapsed_time": "6:56:29", "remaining_time": "3:15:01"}
{"current_steps": 8600, "total_steps": 12480, "loss": 0.0012, "lr": 1.3332417379674426e-06, "epoch": 6.885863035642771, "percentage": 68.91, "elapsed_time": "7:00:59", "remaining_time": "3:09:56"}
{"current_steps": 8700, "total_steps": 12480, "loss": 0.0013, "lr": 1.2718634722903073e-06, "epoch": 6.965959150981178, "percentage": 69.71, "elapsed_time": "7:05:35", "remaining_time": "3:04:54"}
{"current_steps": 8800, "total_steps": 12480, "loss": 0.0007, "lr": 1.2114459422291205e-06, "epoch": 7.045654785742891, "percentage": 70.51, "elapsed_time": "7:10:19", "remaining_time": "2:59:57"}
{"current_steps": 8900, "total_steps": 12480, "loss": 0.0003, "lr": 1.1520364106668342e-06, "epoch": 7.125750901081298, "percentage": 71.31, "elapsed_time": "7:14:48", "remaining_time": "2:54:54"}
{"current_steps": 9000, "total_steps": 12480, "loss": 0.0004, "lr": 1.093681351958383e-06, "epoch": 7.205847016419703, "percentage": 72.12, "elapsed_time": "7:19:18", "remaining_time": "2:49:52"}
{"current_steps": 9000, "total_steps": 12480, "eval_loss": 0.06704169511795044, "epoch": 7.205847016419703, "percentage": 72.12, "elapsed_time": "7:20:56", "remaining_time": "2:50:29"}
{"current_steps": 9100, "total_steps": 12480, "loss": 0.0004, "lr": 1.0364264155751489e-06, "epoch": 7.28594313175811, "percentage": 72.92, "elapsed_time": "7:27:05", "remaining_time": "2:46:03"}
{"current_steps": 9200, "total_steps": 12480, "loss": 0.0004, "lr": 9.803163903946952e-07, "epoch": 7.3660392470965155, "percentage": 73.72, "elapsed_time": "7:31:34", "remaining_time": "2:40:59"}
{"current_steps": 9300, "total_steps": 12480, "loss": 0.0004, "lr": 9.253951696637311e-07, "epoch": 7.446135362434922, "percentage": 74.52, "elapsed_time": "7:36:03", "remaining_time": "2:35:56"}
{"current_steps": 9400, "total_steps": 12480, "loss": 0.0003, "lr": 8.717057166616926e-07, "epoch": 7.526231477773328, "percentage": 75.32, "elapsed_time": "7:41:16", "remaining_time": "2:31:08"}
{"current_steps": 9500, "total_steps": 12480, "loss": 0.0004, "lr": 8.192900310918206e-07, "epoch": 7.606327593111734, "percentage": 76.12, "elapsed_time": "7:45:45", "remaining_time": "2:26:06"}
{"current_steps": 9600, "total_steps": 12480, "loss": 0.0004, "lr": 7.681891162260016e-07, "epoch": 7.68642370845014, "percentage": 76.92, "elapsed_time": "7:50:16", "remaining_time": "2:21:04"}
{"current_steps": 9700, "total_steps": 12480, "loss": 0.0003, "lr": 7.184429468291023e-07, "epoch": 7.766519823788546, "percentage": 77.72, "elapsed_time": "7:54:46", "remaining_time": "2:16:04"}
{"current_steps": 9800, "total_steps": 12480, "loss": 0.0004, "lr": 6.700904378878675e-07, "epoch": 7.846615939126952, "percentage": 78.53, "elapsed_time": "7:59:16", "remaining_time": "2:11:03"}
{"current_steps": 9900, "total_steps": 12480, "loss": 0.0003, "lr": 6.231694141688535e-07, "epoch": 7.926712054465359, "percentage": 79.33, "elapsed_time": "8:03:45", "remaining_time": "2:06:04"}
{"current_steps": 10000, "total_steps": 12480, "loss": 0.0003, "lr": 5.777165806292109e-07, "epoch": 8.006407689227073, "percentage": 80.13, "elapsed_time": "8:08:13", "remaining_time": "2:01:04"}
{"current_steps": 10000, "total_steps": 12480, "eval_loss": 0.06978683918714523, "epoch": 8.006407689227073, "percentage": 80.13, "elapsed_time": "8:09:50", "remaining_time": "2:01:28"}
{"current_steps": 10100, "total_steps": 12480, "loss": 0.0001, "lr": 5.337674937034581e-07, "epoch": 8.086503804565478, "percentage": 80.93, "elapsed_time": "8:15:31", "remaining_time": "1:56:46"}
{"current_steps": 10200, "total_steps": 12480, "loss": 0.0001, "lr": 4.913565334887135e-07, "epoch": 8.166599919903884, "percentage": 81.73, "elapsed_time": "8:20:01", "remaining_time": "1:51:46"}
{"current_steps": 10300, "total_steps": 12480, "loss": 0.0001, "lr": 4.505168768501431e-07, "epoch": 8.246696035242291, "percentage": 82.53, "elapsed_time": "8:24:32", "remaining_time": "1:46:47"}
{"current_steps": 10400, "total_steps": 12480, "loss": 0.0001, "lr": 4.1128047146765936e-07, "epoch": 8.326792150580697, "percentage": 83.33, "elapsed_time": "8:29:02", "remaining_time": "1:41:48"}
{"current_steps": 10500, "total_steps": 12480, "loss": 0.0001, "lr": 3.736780108441762e-07, "epoch": 8.406888265919102, "percentage": 84.13, "elapsed_time": "8:33:32", "remaining_time": "1:36:50"}
{"current_steps": 10600, "total_steps": 12480, "loss": 0.0001, "lr": 3.3773891029497326e-07, "epoch": 8.486984381257509, "percentage": 84.94, "elapsed_time": "8:38:01", "remaining_time": "1:31:52"}
{"current_steps": 10700, "total_steps": 12480, "loss": 0.0, "lr": 3.034912839369447e-07, "epoch": 8.567080496595915, "percentage": 85.74, "elapsed_time": "8:42:32", "remaining_time": "1:26:55"}
{"current_steps": 10800, "total_steps": 12480, "loss": 0.0001, "lr": 2.70961922695743e-07, "epoch": 8.647176611934322, "percentage": 86.54, "elapsed_time": "8:47:03", "remaining_time": "1:21:59"}
{"current_steps": 10900, "total_steps": 12480, "loss": 0.0, "lr": 2.401762733480115e-07, "epoch": 8.727272727272727, "percentage": 87.34, "elapsed_time": "8:51:32", "remaining_time": "1:17:02"}
{"current_steps": 11000, "total_steps": 12480, "loss": 0.0, "lr": 2.1115841861510945e-07, "epoch": 8.807368842611133, "percentage": 88.14, "elapsed_time": "8:56:02", "remaining_time": "1:12:07"}
{"current_steps": 11000, "total_steps": 12480, "eval_loss": 0.08943355828523636, "epoch": 8.807368842611133, "percentage": 88.14, "elapsed_time": "8:57:39", "remaining_time": "1:12:20"}
{"current_steps": 11100, "total_steps": 12480, "loss": 0.0, "lr": 1.8393105832389791e-07, "epoch": 8.88746495794954, "percentage": 88.94, "elapsed_time": "9:03:20", "remaining_time": "1:07:32"}
{"current_steps": 11200, "total_steps": 12480, "loss": 0.0001, "lr": 1.5851549164932118e-07, "epoch": 8.967561073287946, "percentage": 89.74, "elapsed_time": "9:07:51", "remaining_time": "1:02:36"}
{"current_steps": 11300, "total_steps": 12480, "loss": 0.0, "lr": 1.349316004526824e-07, "epoch": 9.047256708049659, "percentage": 90.54, "elapsed_time": "9:12:19", "remaining_time": "0:57:40"}
{"current_steps": 11400, "total_steps": 12480, "loss": 0.0, "lr": 1.1319783372863601e-07, "epoch": 9.127352823388065, "percentage": 91.35, "elapsed_time": "9:16:49", "remaining_time": "0:52:45"}
{"current_steps": 11500, "total_steps": 12480, "loss": 0.0, "lr": 9.333119317307598e-08, "epoch": 9.207448938726472, "percentage": 92.15, "elapsed_time": "9:22:55", "remaining_time": "0:47:58"}
{"current_steps": 11600, "total_steps": 12480, "loss": 0.0, "lr": 7.534721988320143e-08, "epoch": 9.287545054064879, "percentage": 92.95, "elapsed_time": "9:27:23", "remaining_time": "0:43:02"}
{"current_steps": 11700, "total_steps": 12480, "loss": 0.0, "lr": 5.92599822001666e-08, "epoch": 9.367641169403283, "percentage": 93.75, "elapsed_time": "9:31:54", "remaining_time": "0:38:07"}
{"current_steps": 11800, "total_steps": 12480, "loss": 0.0, "lr": 4.508206470382554e-08, "epoch": 9.44773728474169, "percentage": 94.55, "elapsed_time": "9:36:24", "remaining_time": "0:33:12"}
{"current_steps": 11900, "total_steps": 12480, "loss": 0.0, "lr": 3.2824558368179384e-08, "epoch": 9.527833400080096, "percentage": 95.35, "elapsed_time": "9:40:53", "remaining_time": "0:28:18"}
{"current_steps": 12000, "total_steps": 12480, "loss": 0.0, "lr": 2.2497051885228825e-08, "epoch": 9.607929515418503, "percentage": 96.15, "elapsed_time": "9:45:23", "remaining_time": "0:23:24"}
{"current_steps": 12000, "total_steps": 12480, "eval_loss": 0.09308738261461258, "epoch": 9.607929515418503, "percentage": 96.15, "elapsed_time": "9:47:00", "remaining_time": "0:23:28"}
{"current_steps": 12100, "total_steps": 12480, "loss": 0.0, "lr": 1.4107624164019229e-08, "epoch": 9.688025630756908, "percentage": 96.96, "elapsed_time": "9:52:45", "remaining_time": "0:18:36"}
{"current_steps": 12200, "total_steps": 12480, "loss": 0.0, "lr": 7.662838010742413e-09, "epoch": 9.768121746095314, "percentage": 97.76, "elapsed_time": "9:57:15", "remaining_time": "0:13:42"}
{"current_steps": 12300, "total_steps": 12480, "loss": 0.0, "lr": 3.1677349948461277e-09, "epoch": 9.84821786143372, "percentage": 98.56, "elapsed_time": "10:02:03", "remaining_time": "0:08:48"}
{"current_steps": 12400, "total_steps": 12480, "loss": 0.0, "lr": 6.258315051568819e-10, "epoch": 9.928313976772127, "percentage": 99.36, "elapsed_time": "10:06:35", "remaining_time": "0:03:54"}
{"current_steps": 12480, "total_steps": 12480, "epoch": 9.992390869042852, "percentage": 100.0, "elapsed_time": "10:11:26", "remaining_time": "0:00:00"}